
import numpy as np
import tensorflow as tf
from tensorflow import keras
import pandas as pd
import seaborn as sns
from pylab import rcParams
import matplotlib.pyplot as plt
from matplotlib import rc
from sklearn.model_selection import train_test_split
from pandas.plotting import register_matplotlib_converters

%matplotlib inline
%config InlineBackend.figure_format='retina'

register_matplotlib_converters()
sns.set(style='whitegrid', palette='muted', font_scale=1.5)

rcParams['figure.figsize'] = 22, 10

RANDOM_SEED = 42

np.random.seed(RANDOM_SEED)
tf.random.set_seed(RANDOM_SEED)
import warnings
warnings.filterwarnings("ignore")


from statsmodels.graphics.tsaplots import plot_acf,plot_pacf 
from statsmodels.tsa.seasonal import seasonal_decompose      
from pmdarima import auto_arima


df=pd.read_csv('Book1.csv',thousands=',')

df


df['Date'] = pd.to_datetime(df['Date']).dt.strftime('%d-%m-%Y')


df['Date'] = pd.to_datetime(df['Date'])


df=df.set_index('Date')

df


df.index

DatetimeIndex(['2022-02-25', '2022-02-24', '2022-02-23', '2022-02-22',
               '2022-02-21', '2022-02-18', '2022-02-17', '2022-02-16',
               '2022-02-15', '2022-02-14',
               ...
               '2011-12-22', '2011-12-21', '2011-12-20', '2011-12-19',
               '2011-12-17', '2011-12-16', '2011-12-15', '2011-12-14',
               '2011-12-13', '2011-12-12'],
              dtype='datetime64[ns]', name='Date', length=2742, freq=None)

df


pd.date_range(start = '2011-12-15', end = '2011-12-13' ).difference(df.index)

DatetimeIndex([], dtype='datetime64[ns]', freq=None)


df.reindex(pd.date_range('2011-12-15', '2011-12-12')).isnull().all(1)

Series([], Freq: D, dtype: bool)


df.info()

<class 'pandas.core.frame.DataFrame'>
DatetimeIndex: 2742 entries, 2022-02-25 to 2011-12-12
Data columns (total 6 columns):
 #   Column  Non-Null Count  Dtype 
---  ------  --------------  ----- 
 0   Price   2742 non-null   int64 
 1   Open    2742 non-null   int64 
 2   High    2742 non-null   int64 
 3   Low     2742 non-null   int64 
 4   Volume  2742 non-null   object
 5   Chg%    2742 non-null   object
dtypes: int64(4), object(2)
memory usage: 230.0+ KB


df=df.drop(columns=['Chg%'])


df.columns

Index(['Price', 'Open', 'High', 'Low', 'Volume'], dtype='object')


df['Volume']=df['Volume'].astype(str)


df['Volume'] = df.apply(lambda x: x['Volume'][:-1], axis = 1)


df['Volume'] = df['Volume'].astype(str)
df['Volume']=pd.to_numeric(df['Volume'])


df['Volume'] = df['Volume']*1000


df=df.dropna()


cols = df.columns
for col in cols:
    df[col]=df[col].astype(int)

df


df.info()

<class 'pandas.core.frame.DataFrame'>
DatetimeIndex: 2709 entries, 2022-02-25 to 2011-12-12
Data columns (total 5 columns):
 #   Column  Non-Null Count  Dtype
---  ------  --------------  -----
 0   Price   2709 non-null   int32
 1   Open    2709 non-null   int32
 2   High    2709 non-null   int32
 3   Low     2709 non-null   int32
 4   Volume  2709 non-null   int32
dtypes: int32(5)
memory usage: 74.1 KB


df['Price'].plot()

<AxesSubplot:xlabel='Date'>


df.shape

(2709, 5)


df['year'] = df.index.year
df['day_of_month'] = df.index.day
df['day_of_week'] = df.index.dayofweek
df['month'] = df.index.month

df


sns.lineplot(x=df.index,y="Price",data=df)

<AxesSubplot:xlabel='Date', ylabel='Price'>


fig,(ax1, ax2)= plt.subplots(nrows=2)
fig.set_size_inches(10, 10)

sns.pointplot(data=df, x='year', y='Price', ax=ax1)
sns.pointplot(data=df, x='year', y='Volume', ax=ax2)

<AxesSubplot:xlabel='year', ylabel='Volume'>


from sklearn.preprocessing import RobustScaler
from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import MinMaxScaler


df.columns

Index(['Price', 'Open', 'High', 'Low', 'Volume', 'year', 'day_of_month',
       'day_of_week', 'month'],
      dtype='object')


train_size = int(len(df) * 0.9)
test_size = len(df) - train_size
train, test = df.iloc[0:train_size], df.iloc[train_size:len(df)]
print(len(train), len(test))

2438 271


feature_cols = ['Open', 'High', 'Low', 'Volume']
feature_transformer = StandardScaler()
price_transformer = StandardScaler()

feature_transformer = feature_transformer.fit(train[feature_cols].to_numpy())
price_transformer = price_transformer.fit(train[['Price']])

train.loc[:, feature_cols] = feature_transformer.transform(train[feature_cols].to_numpy())
train['Price'] = price_transformer.transform(train[['Price']])

test.loc[:, feature_cols] = feature_transformer.transform(test[feature_cols].to_numpy())
test['Price'] = price_transformer.transform(test[['Price']])


def create_dataset(X, y, time_steps=1):
    Xs, ys = [], []
    for i in range(len(X) - time_steps):
        v = X.iloc[i:(i + time_steps)].values
        Xs.append(v)        
        ys.append(y.iloc[i + time_steps])
    return np.array(Xs), np.array(ys)


time_steps = 10

X_train, y_train = create_dataset(train, train.Price, time_steps)
X_test, y_test = create_dataset(test, test.Price, time_steps)

print(X_train.shape, y_train.shape)

(2428, 10, 9) (2428,)


model = keras.Sequential()
model.add(
    keras.layers.LSTM(128,activation='relu', input_shape=(X_train.shape[1], X_train.shape[2]),return_sequences=True)
)
model.add(
    keras.layers.LSTM(50,activation='relu',return_sequences=False)
)

model.add(keras.layers.Dropout(rate=0.2))
model.add(keras.layers.Dense(units=1))
model.compile(loss='mean_squared_error', optimizer='adam')


history = model.fit(
    X_train, y_train, 
    epochs=25, 
    batch_size=10, 
    validation_split=0.1,
    verbose=1,
    shuffle=True
)

Epoch 1/25
219/219 [==============================] - 5s 11ms/step - loss: 43582.6523 - val_loss: 21.8553
Epoch 2/25
219/219 [==============================] - 2s 10ms/step - loss: 259.0980 - val_loss: 2.7064
Epoch 3/25
219/219 [==============================] - 2s 11ms/step - loss: 101.4543 - val_loss: 5.0249
Epoch 4/25
219/219 [==============================] - 2s 11ms/step - loss: 40.1113 - val_loss: 4.1428
Epoch 5/25
219/219 [==============================] - 2s 10ms/step - loss: 31.3178 - val_loss: 2.7662
Epoch 6/25
219/219 [==============================] - 2s 10ms/step - loss: 25.4493 - val_loss: 4.9744
Epoch 7/25
219/219 [==============================] - 2s 10ms/step - loss: 24.3876 - val_loss: 3.1609
Epoch 8/25
219/219 [==============================] - 2s 10ms/step - loss: 19.7206 - val_loss: 0.6123
Epoch 9/25
219/219 [==============================] - 2s 9ms/step - loss: 17.2330 - val_loss: 2.5818
Epoch 10/25
219/219 [==============================] - 2s 10ms/step - loss: 14.6701 - val_loss: 1.9308
Epoch 11/25
219/219 [==============================] - 2s 9ms/step - loss: 11.4791 - val_loss: 1.3063
Epoch 12/25
219/219 [==============================] - 2s 9ms/step - loss: 9.2900 - val_loss: 2.3369
Epoch 13/25
219/219 [==============================] - 2s 10ms/step - loss: 7.8894 - val_loss: 1.4994
Epoch 14/25
219/219 [==============================] - 2s 9ms/step - loss: 6.0399 - val_loss: 0.7097
Epoch 15/25
219/219 [==============================] - 2s 9ms/step - loss: 4.9023 - val_loss: 1.2042
Epoch 16/25
219/219 [==============================] - 2s 10ms/step - loss: 4.3718 - val_loss: 1.1122
Epoch 17/25
219/219 [==============================] - 2s 9ms/step - loss: 3.6000 - val_loss: 0.9537
Epoch 18/25
219/219 [==============================] - 2s 10ms/step - loss: 3.7488 - val_loss: 1.0318
Epoch 19/25
219/219 [==============================] - 2s 9ms/step - loss: 3.3545 - val_loss: 1.2917
Epoch 20/25
219/219 [==============================] - 2s 10ms/step - loss: 3.3355 - val_loss: 0.8357
Epoch 21/25
219/219 [==============================] - 2s 10ms/step - loss: 3.2001 - val_loss: 1.7094
Epoch 22/25
219/219 [==============================] - 2s 9ms/step - loss: 2.9948 - val_loss: 1.3742
Epoch 23/25
219/219 [==============================] - 2s 9ms/step - loss: 2.8705 - val_loss: 2.2006
Epoch 24/25
219/219 [==============================] - 2s 9ms/step - loss: 2.5183 - val_loss: 1.2723
Epoch 25/25
219/219 [==============================] - 2s 9ms/step - loss: 2.3754 - val_loss: 0.2513


plt.plot(history.history['loss'], label='train')
plt.plot(history.history['val_loss'], label='test')
plt.legend();


y_pred = model.predict(X_test)


y_train_inv = price_transformer.inverse_transform(y_train.reshape(1, -1))
y_test_inv = price_transformer.inverse_transform(y_test.reshape(1, -1))
y_pred_inv = price_transformer.inverse_transform(y_pred)


plt.plot(y_test_inv.flatten(), marker='.', label="true")
plt.plot(y_pred_inv.flatten(), 'r', label="prediction")
plt.ylabel('Price')
plt.xlabel('Time Step')
plt.legend()
plt.show();


from sklearn.metrics import mean_absolute_error as mae
from sklearn.metrics import mean_squared_error as mse
from sklearn.metrics import r2_score as r2s
from numpy import sqrt


mae1=mae(y_test_inv.reshape(-1,1),y_pred_inv)
mse1=mse(y_test_inv.reshape(-1,1),y_pred_inv)
rmse1=sqrt(mse1)


mae1,rmse1,mse1

(352.1586053490182, 492.4970562611148, 242553.35042586364)


np.mean(y_test_inv)

5080.567049808429

df


import numpy as np
from keras.models import Sequential
from keras.layers import LSTM
from keras.layers import Dropout
from keras.layers import Dense
import pandas as pd
from matplotlib import pyplot as plt
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import mean_absolute_error as mae
from sklearn.metrics import mean_squared_error as mse
from sklearn.metrics import r2_score as r2s
from math import sqrt
import os


dfOil=df
dfOilPrice=dfOil['Price'].astype(float)


scaler=StandardScaler()
scaler=scaler.fit(dfOilPrice.values.reshape(-1, 1))
dfOilPriceScaled=scaler.transform(dfOilPrice.values.reshape(-1, 1))


oilPX=[]
oilPY=[]


nextPrd=1
windSz=14

for i in range(windSz, len(dfOilPriceScaled)-nextPrd+1):    
    oilPX.append(dfOilPriceScaled[i-windSz:i])
    oilPY.append(dfOilPriceScaled[i+nextPrd-1:i+nextPrd,0])

oilPX,oilPY=np.array(oilPX),np.array(oilPY)


print('dfOil shape= {}.'.format(dfOil.shape))
print('dfOilPriceScaled shape= {}.'.format(dfOilPriceScaled.shape))
print('oilPX shape== {}.'.format(oilPX.shape))
print('oilPY shape== {}.'.format(oilPY.shape))

dfOil shape= (2709, 9).
dfOilPriceScaled shape= (2709, 1).
oilPX shape== (2695, 14, 1).
oilPY shape== (2695, 1).


model=Sequential()
model.add(LSTM(100, activation='relu', input_shape=(oilPX.shape[1], oilPX.shape[2]), return_sequences=True))
model.add(LSTM(50, activation= 'relu',return_sequences=False))
model.add(Dropout(0.2))
model.add(Dense(oilPY.shape[1]))
model.compile(optimizer='adam',loss='mse')
history=model.fit(oilPX,oilPY,epochs=25,batch_size=16, validation_split=0.1,verbose=1)

Epoch 1/25
152/152 [==============================] - 4s 14ms/step - loss: 0.1242 - val_loss: 0.0886
Epoch 2/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0451 - val_loss: 0.0871
Epoch 3/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0383 - val_loss: 0.0935
Epoch 4/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0349 - val_loss: 0.0881
Epoch 5/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0316 - val_loss: 0.0908
Epoch 6/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0313 - val_loss: 0.0885
Epoch 7/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0310 - val_loss: 0.0871
Epoch 8/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0300 - val_loss: 0.0879
Epoch 9/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0298 - val_loss: 0.0878
Epoch 10/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0290 - val_loss: 0.0883
Epoch 11/25
152/152 [==============================] - 2s 14ms/step - loss: 0.0279 - val_loss: 0.0883
Epoch 12/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0263 - val_loss: 0.0886
Epoch 13/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0290 - val_loss: 0.0905
Epoch 14/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0270 - val_loss: 0.0885
Epoch 15/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0253 - val_loss: 0.0908
Epoch 16/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0274 - val_loss: 0.0884
Epoch 17/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0245 - val_loss: 0.0907
Epoch 18/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0264 - val_loss: 0.0927
Epoch 19/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0257 - val_loss: 0.0929
Epoch 20/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0259 - val_loss: 0.0923
Epoch 21/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0241 - val_loss: 0.0914
Epoch 22/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0250 - val_loss: 0.0940
Epoch 23/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0263 - val_loss: 0.0924
Epoch 24/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0229 - val_loss: 0.0947
Epoch 25/25
152/152 [==============================] - 2s 12ms/step - loss: 0.0243 - val_loss: 0.0946


fig, ax = plt.subplots(figsize=(15, 5))
fig.subplots_adjust(bottom=0.15, left=0.2)
ax.plot(range(0,len(history.history['loss'])),history.history['loss'],color='blue',label='loss')
ax.plot(range(0,len(history.history['val_loss'])),history.history['val_loss'],color='red',label='val_loss')
ax.set_xlabel('loss')
ax.set_ylabel('val loss')
plt.legend()
plt.show()


forecastD=60

predictedForDays=model.predict(oilPX[-forecastD:])
actualOilPForDays=dfOil['Price'][-forecastD:]
predictedForDaysInn=scaler.inverse_transform(predictedForDays)


fig, ax = plt.subplots(figsize=(15, 5))
fig.subplots_adjust(bottom=0.15, left=0.2)
ax.plot(range(0,len(predictedForDaysInn)),dfOil['Price'][-forecastD:],color='blue',label='True Price of data')
ax.plot(range(0,len(predictedForDaysInn)),predictedForDaysInn,color='red',label='predicted')
ax.set_xlabel('true price')
ax.set_ylabel('predicted')
plt.legend()
plt.show()


fig, ax = plt.subplots(figsize=(15, 5))
fig.subplots_adjust(bottom=0.15, left=0.2)
ax.plot(range(0,len(dfOil)-forecastD),dfOil['Price'][0:len(dfOil)-forecastD],color='blue',label='True Price of data')
ax.plot(range(len(dfOil)-forecastD,len(dfOil)),predictedForDaysInn,color='red',label='predicted')
ax.set_xlabel('true price')
ax.set_ylabel('predicted')
plt.legend()
plt.show()


mae1=mae(actualOilPForDays,predictedForDaysInn)
mse1=mse(actualOilPForDays,predictedForDaysInn)
print(mse1)
rmse1=sqrt(mse1)
r2_score=r2s(actualOilPForDays,predictedForDaysInn)
print(r2_score)
n=forecastD
k=1
adjr=1-(((1-r2_score)*(n-1))/(n-k-1))
print(adjr)

9307.512559910616
0.7509149815060313
0.7466204122216525

df


df.info()

<class 'pandas.core.frame.DataFrame'>
DatetimeIndex: 2709 entries, 2022-02-25 to 2011-12-12
Data columns (total 9 columns):
 #   Column        Non-Null Count  Dtype
---  ------        --------------  -----
 0   Price         2709 non-null   int32
 1   Open          2709 non-null   int32
 2   High          2709 non-null   int32
 3   Low           2709 non-null   int32
 4   Volume        2709 non-null   int32
 5   year          2709 non-null   int64
 6   day_of_month  2709 non-null   int64
 7   day_of_week   2709 non-null   int64
 8   month         2709 non-null   int64
dtypes: int32(5), int64(4)
memory usage: 158.7 KB


df['Price'].resample('Y').mean().plot.bar(title='Yearly average oil prices')

<AxesSubplot:title={'center':'Yearly average oil prices'}, xlabel='Date'>


df['Price'].resample('Y').plot()

Date
2011-12-31    AxesSubplot(0.125,0.2;0.775x0.68)
2012-12-31    AxesSubplot(0.125,0.2;0.775x0.68)
2013-12-31    AxesSubplot(0.125,0.2;0.775x0.68)
2014-12-31    AxesSubplot(0.125,0.2;0.775x0.68)
2015-12-31    AxesSubplot(0.125,0.2;0.775x0.68)
2016-12-31    AxesSubplot(0.125,0.2;0.775x0.68)
2017-12-31    AxesSubplot(0.125,0.2;0.775x0.68)
2018-12-31    AxesSubplot(0.125,0.2;0.775x0.68)
2019-12-31    AxesSubplot(0.125,0.2;0.775x0.68)
2020-12-31    AxesSubplot(0.125,0.2;0.775x0.68)
2021-12-31    AxesSubplot(0.125,0.2;0.775x0.68)
2022-12-31    AxesSubplot(0.125,0.2;0.775x0.68)
Freq: A-DEC, Name: Price, dtype: object


df['Price'].resample('Y').plot()
df.rolling(window=150).mean()['Price'].plot(color='black');


df['Price'].expanding(min_periods=150).mean().plot(figsize=(12,5));


df[df<5]=1


from statsmodels.tsa.seasonal import seasonal_decompose

result = seasonal_decompose(df['Price'].values, model='multiplicative',period=12)  # model='mul' also works
result.plot();


df['6-month-SMA'] = df['Price'].rolling(window=6).mean()
df['12-month-SMA'] = df['Price'].rolling(window=12).mean()


df['12-month-SMA'].plot(figsize=(15,5),legend=True)

<AxesSubplot:xlabel='Date'>


df['EWMA12']=df['Price'].ewm(span=12,adjust=True).mean()


df['EWMA12'].plot()

<AxesSubplot:xlabel='Date'>


from statsmodels.tsa.holtwinters import ExponentialSmoothing


df['TESadd12'] = ExponentialSmoothing(df['Price'],trend='add',seasonal='add',seasonal_periods=12).fit().fittedvalues


df['TESmul12'] = ExponentialSmoothing(df['Price'],trend='mul',seasonal='mul',seasonal_periods=12).fit().fittedvalues


df[['TESadd12','TESmul12']].iloc[:150].plot(figsize=(12,6)).autoscale(axis='x',tight=True);

df


df2=df

df2


df2=df2.drop(columns=['year', 'day_of_month',
       'day_of_week', 'month', '6-month-SMA', '12-month-SMA', 'EWMA12',
       'TESadd12', 'TESmul12'])


df2.columns

Index(['Price', 'Open', 'High', 'Low', 'Volume'], dtype='object')

df2


df3=df2.resample('W').mean().ffill()


df3.index

DatetimeIndex(['2011-12-18', '2011-12-25', '2012-01-01', '2012-01-08',
               '2012-01-15', '2012-01-22', '2012-01-29', '2012-02-05',
               '2012-02-12', '2012-02-19',
               ...
               '2022-10-02', '2022-10-09', '2022-10-16', '2022-10-23',
               '2022-10-30', '2022-11-06', '2022-11-13', '2022-11-20',
               '2022-11-27', '2022-12-04'],
              dtype='datetime64[ns]', name='Date', length=573, freq='W-SUN')


pd.set_option('display.max_rows', None)
pd.set_option('display.max_columns', None)
pd.set_option('display.width', None)
pd.set_option('display.max_colwidth', -1)


df3=df3[:'2022-02-27']

df3


len(df3)

533


len(df3)

533


df3=df3.sort_index()


 for i in df3.columns:
     df3[i]=df3[i].fillna(int(df[i].mean()))


train_data = df3.iloc[:500] 
test_data = df3.iloc[500:]


from statsmodels.tsa.holtwinters import ExponentialSmoothing

fitted_model = ExponentialSmoothing(train_data['Price'],trend='mul',seasonal='mul',seasonal_periods=12).fit()


test_predictions = fitted_model.forecast(33).rename('HW Forecast')


train_data['Price'].plot(legend=True,label='TRAIN')
test_data['Price'].plot(legend=True,label='TEST',figsize=(12,8))

<AxesSubplot:xlabel='Date'>


test_data['Price'].plot(legend=True,label='TEST',figsize=(12,8))
test_predictions.plot(legend=True)

<AxesSubplot:xlabel='Date'>


test_predictions.plot()

<AxesSubplot:>


train_data['Price'].plot(legend=True,label='TRAIN')
test_data['Price'].plot(legend=True,label='TEST',figsize=(12,8))
test_predictions.plot(legend=True,label='PREDICTION')

<AxesSubplot:xlabel='Date'>


from statsmodels.tools.eval_measures import rmse

error = rmse(test_data['Price'], test_predictions)
print(f'RMSE Error: {error:11.10}')

RMSE Error: 758.7116377


import warnings
warnings.filterwarnings("ignore")


from statsmodels.tsa.stattools import acovf,acf,pacf,pacf_yw,pacf_ols


from pandas.plotting import lag_plot

lag_plot(df3['Price']);

*c* argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with *x* & *y*.  Please use the *color* keyword-argument or provide a 2D array with a single row if you intend to specify the same RGB or RGBA value for all points.


from statsmodels.graphics.tsaplots import plot_acf,plot_pacf


acf(df3['Price']).shape

(28,)


title = 'Autocorrelation: Price'
lags = 40
plot_acf(df3['Price'],title=title,lags=lags);


title='Partial Autocorrelation: Price'
lags=40
plot_pacf(df3['Price'],title=title,lags=lags);


from statsmodels.tsa.ar_model import AR,ARResults,AutoReg


train = df.iloc[:500]
test = df.iloc[500:]


model = AutoReg(train['Price'],lags=1)
AR1fit = model.fit()


start=len(train)
end=len(train)+len(test)-1
predictions1 = AR1fit.predict(start=start, end=end, dynamic=False).rename('AR(1) Predictions')


predictions1

2438    0.360253
2439    0.358134
2440    0.356023
2441    0.353920
2442    0.351826
2443    0.349740
2444    0.347661
2445    0.345591
2446    0.343529
2447    0.341475
2448    0.339428
2449    0.337390
2450    0.335359
2451    0.333336
2452    0.331322
2453    0.329314
2454    0.327315
2455    0.325323
2456    0.323339
2457    0.321363
2458    0.319394
2459    0.317433
2460    0.315480
2461    0.313534
2462    0.311595
2463    0.309665
2464    0.307741
2465    0.305825
2466    0.303916
2467    0.302015
2468    0.300121
2469    0.298234
2470    0.296355
2471    0.294483
2472    0.292618
2473    0.290761
2474    0.288910
2475    0.287067
2476    0.285230
2477    0.283401
2478    0.281579
2479    0.279764
2480    0.277956
2481    0.276155
2482    0.274361
2483    0.272574
2484    0.270794
2485    0.269020
2486    0.267254
2487    0.265494
2488    0.263741
2489    0.261995
2490    0.260256
2491    0.258523
2492    0.256797
2493    0.255078
2494    0.253365
2495    0.251659
2496    0.249960
2497    0.248267
2498    0.246581
2499    0.244901
2500    0.243227
2501    0.241560
2502    0.239900
2503    0.238246
2504    0.236598
2505    0.234957
2506    0.233322
2507    0.231693
2508    0.230071
2509    0.228455
2510    0.226845
2511    0.225242
2512    0.223644
2513    0.222053
2514    0.220468
2515    0.218889
2516    0.217316
2517    0.215749
2518    0.214188
2519    0.212634
2520    0.211085
2521    0.209542
2522    0.208005
2523    0.206475
2524    0.204950
2525    0.203431
2526    0.201917
2527    0.200410
2528    0.198909
2529    0.197413
2530    0.195923
2531    0.194439
2532    0.192960
2533    0.191488
2534    0.190021
2535    0.188559
2536    0.187103
2537    0.185653
2538    0.184209
2539    0.182770
2540    0.181336
2541    0.179909
2542    0.178486
2543    0.177069
2544    0.175658
2545    0.174252
2546    0.172852
2547    0.171457
2548    0.170067
2549    0.168683
2550    0.167304
2551    0.165930
2552    0.164562
2553    0.163199
2554    0.161841
2555    0.160488
2556    0.159141
2557    0.157799
2558    0.156462
2559    0.155130
2560    0.153804
2561    0.152482
2562    0.151166
2563    0.149854
2564    0.148548
2565    0.147247
2566    0.145951
2567    0.144659
2568    0.143373
2569    0.142092
2570    0.140816
2571    0.139544
2572    0.138278
2573    0.137017
2574    0.135760
2575    0.134508
2576    0.133261
2577    0.132019
2578    0.130782
2579    0.129549
2580    0.128321
2581    0.127098
2582    0.125880
2583    0.124666
2584    0.123457
2585    0.122253
2586    0.121053
2587    0.119858
2588    0.118668
2589    0.117482
2590    0.116301
2591    0.115124
2592    0.113952
2593    0.112784
2594    0.111621
2595    0.110463
2596    0.109309
2597    0.108159
2598    0.107014
2599    0.105873
2600    0.104737
2601    0.103605
2602    0.102477
2603    0.101354
2604    0.100235
2605    0.099120
2606    0.098010
2607    0.096904
2608    0.095802
2609    0.094705
2610    0.093611
2611    0.092522
2612    0.091438
2613    0.090357
2614    0.089281
2615    0.088208
2616    0.087140
2617    0.086076
2618    0.085016
2619    0.083960
2620    0.082909
2621    0.081861
2622    0.080817
2623    0.079778
2624    0.078742
2625    0.077711
2626    0.076683
2627    0.075659
2628    0.074640
2629    0.073624
2630    0.072612
2631    0.071604
2632    0.070600
2633    0.069600
2634    0.068604
2635    0.067611
2636    0.066623
2637    0.065638
2638    0.064657
2639    0.063680
2640    0.062706
2641    0.061737
2642    0.060771
2643    0.059809
2644    0.058850
2645    0.057895
2646    0.056944
2647    0.055997
2648    0.055053
2649    0.054113
2650    0.053177
2651    0.052244
2652    0.051315
2653    0.050389
2654    0.049467
2655    0.048548
2656    0.047633
2657    0.046722
2658    0.045814
2659    0.044910
2660    0.044009
2661    0.043111
2662    0.042217
2663    0.041327
2664    0.040440
2665    0.039556
2666    0.038676
2667    0.037799
2668    0.036925
2669    0.036055
2670    0.035189
2671    0.034325
2672    0.033465
2673    0.032609
2674    0.031755
2675    0.030905
2676    0.030058
2677    0.029215
2678    0.028374
2679    0.027537
2680    0.026703
2681    0.025873
2682    0.025046
2683    0.024221
2684    0.023400
2685    0.022582
2686    0.021768
2687    0.020956
2688    0.020148
2689    0.019343
2690    0.018540
2691    0.017741
2692    0.016945
2693    0.016152
2694    0.015363
2695    0.014576
2696    0.013792
2697    0.013011
2698    0.012234
2699    0.011459
2700    0.010687
2701    0.009918
2702    0.009153
2703    0.008390
2704    0.007630
2705    0.006873
2706    0.006119
2707    0.005368
2708    0.004620
Name: AR(1) Predictions, dtype: float64


ARfit = model.fit()

print(f'Coefficients:\n{ARfit.params}')

Coefficients:
const      -0.000727
Price.L1    0.996138
dtype: float64


start = len(train)
end = len(train)+len(test)-1
rename = f'AR(11) Predictions'

predictions11 = ARfit.predict(start=start,end=end,dynamic=False).rename(rename)


from sklearn.metrics import mean_squared_error

labels = ['AR(1)','AR(11)']
preds = [predictions1,  predictions11]  # these are variables, not strings!

for i in range(2):
    error = mean_squared_error(test['Price'], preds[i])
    print(f'{labels[i]} Error: {error:11.10}')

AR(1) Error: 0.424256674
AR(11) Error: 0.424256674


from statsmodels.tsa.stattools import ccovf,ccf
from statsmodels.tsa.stattools import adfuller,kpss,coint,bds,q_stat,grangercausalitytests,levinson_durbin
from statsmodels.tools.eval_measures import mse, rmse, meanabs


from statsmodels.tsa.stattools import adfuller

def adf_test(series,title=''):
    """
    Pass in a time series and an optional title, returns an ADF report
    """
    print(f'Augmented Dickey-Fuller Test: {title}')
    result = adfuller(series.dropna(),autolag='AIC') # .dropna() handles differenced data
    
    labels = ['ADF test statistic','p-value','# lags used','# observations']
    out = pd.Series(result[0:4],index=labels)

    for key,val in result[4].items():
        out[f'critical value ({key})']=val
        
    print(out.to_string())          # .to_string() removes the line "dtype: float64"
    
    if result[1] <= 0.05:
        print("Strong evidence against the null hypothesis")
        print("Reject the null hypothesis")
        print("Data has no unit root and is stationary")
    else:
        print("Weak evidence against the null hypothesis")
        print("Fail to reject the null hypothesis")
        print("Data has a unit root and is non-stationary")


adf_test(df3['Price'])

Augmented Dickey-Fuller Test: 
ADF test statistic     -0.895398  
p-value                 0.789484  
# lags used             17.000000 
# observations          515.000000
critical value (1%)    -3.443112  
critical value (5%)    -2.867168  
critical value (10%)   -2.569768  
Weak evidence against the null hypothesis
Fail to reject the null hypothesis
Data has a unit root and is non-stationary


from pmdarima import auto_arima

import warnings
warnings.filterwarnings("ignore")

df3


len(df3)

533


auto_arima(df3['Price'])

ARIMA(order=(5, 1, 2), scoring_args={}, suppress_warnings=True,
      with_intercept=False)


auto_arima(df3['Price'],error_action='ignore').summary()


stepwise_fit = auto_arima(df3['Price'], start_p=1, start_q=1,
                          max_p=3, max_q=3, m=12,
                          start_P=0, seasonal=True,
                          d=None, D=1, trace=True,
                          error_action='ignore',   # we don't want to know if an order does not work
                          suppress_warnings=True,  # we don't want convergence warnings
                          stepwise=True)           # set to stepwise

stepwise_fit.summary()

Performing stepwise search to minimize aic
 ARIMA(1,0,1)(0,1,1)[12] intercept   : AIC=inf, Time=2.04 sec
 ARIMA(0,0,0)(0,1,0)[12] intercept   : AIC=8376.870, Time=0.03 sec
 ARIMA(1,0,0)(1,1,0)[12] intercept   : AIC=7968.093, Time=0.99 sec
 ARIMA(0,0,1)(0,1,1)[12] intercept   : AIC=8190.221, Time=0.73 sec
 ARIMA(0,0,0)(0,1,0)[12]             : AIC=8375.452, Time=0.02 sec
 ARIMA(1,0,0)(0,1,0)[12] intercept   : AIC=8176.814, Time=0.10 sec
 ARIMA(1,0,0)(2,1,0)[12] intercept   : AIC=7891.066, Time=3.20 sec
 ARIMA(1,0,0)(2,1,1)[12] intercept   : AIC=inf, Time=6.00 sec
 ARIMA(1,0,0)(1,1,1)[12] intercept   : AIC=7834.519, Time=2.36 sec
 ARIMA(1,0,0)(0,1,1)[12] intercept   : AIC=inf, Time=1.23 sec
 ARIMA(1,0,0)(1,1,2)[12] intercept   : AIC=7838.462, Time=5.99 sec
 ARIMA(1,0,0)(0,1,2)[12] intercept   : AIC=7840.511, Time=5.03 sec
 ARIMA(1,0,0)(2,1,2)[12] intercept   : AIC=inf, Time=6.00 sec
 ARIMA(0,0,0)(1,1,1)[12] intercept   : AIC=8357.348, Time=0.46 sec
 ARIMA(2,0,0)(1,1,1)[12] intercept   : AIC=7804.944, Time=3.34 sec
 ARIMA(2,0,0)(0,1,1)[12] intercept   : AIC=inf, Time=2.00 sec
 ARIMA(2,0,0)(1,1,0)[12] intercept   : AIC=7950.378, Time=1.21 sec
 ARIMA(2,0,0)(2,1,1)[12] intercept   : AIC=7807.267, Time=6.12 sec
 ARIMA(2,0,0)(1,1,2)[12] intercept   : AIC=inf, Time=7.32 sec
 ARIMA(2,0,0)(0,1,0)[12] intercept   : AIC=8164.453, Time=0.13 sec
 ARIMA(2,0,0)(0,1,2)[12] intercept   : AIC=7818.176, Time=5.63 sec
 ARIMA(2,0,0)(2,1,0)[12] intercept   : AIC=7856.419, Time=4.20 sec
 ARIMA(2,0,0)(2,1,2)[12] intercept   : AIC=inf, Time=7.50 sec
 ARIMA(3,0,0)(1,1,1)[12] intercept   : AIC=inf, Time=3.96 sec
 ARIMA(2,0,1)(1,1,1)[12] intercept   : AIC=7843.774, Time=3.21 sec
 ARIMA(1,0,1)(1,1,1)[12] intercept   : AIC=inf, Time=3.00 sec
 ARIMA(3,0,1)(1,1,1)[12] intercept   : AIC=7859.098, Time=4.21 sec
 ARIMA(2,0,0)(1,1,1)[12]             : AIC=inf, Time=3.34 sec

Best model:  ARIMA(2,0,0)(1,1,1)[12] intercept
Total fit time: 89.378 seconds


from statsmodels.tsa.statespace.tools import diff
df3['d1'] = diff(df3['Price'],k_diff=1)
adf_test(df3['d1'],'Diff Price 1')

Augmented Dickey-Fuller Test: Diff Price 1
ADF test statistic     -6.116961e+00
p-value                 9.045948e-08
# lags used             1.600000e+01
# observations          5.150000e+02
critical value (1%)    -3.443112e+00
critical value (5%)    -2.867168e+00
critical value (10%)   -2.569768e+00
Strong evidence against the null hypothesis
Reject the null hypothesis
Data has no unit root and is stationary


len(df3)

533


train = df3.iloc[:500]
test = df3.iloc[500:]


import statsmodels.api as sm


results = sm.tsa.statespace.SARIMAX(train['Price'],order=(5,1,12),
                                enforce_stationarity=False, enforce_invertibility=False).fit()
results.summary()


# Obtain predicted values
start=len(train)
end=len(train)+len(test)-1
predictions = results.predict(start=start, end=end, dynamic=False, typ='levels').rename('SARIMA Predictions')


test['Price'].plot(legend=True,figsize=(12,6))
predictions.plot(legend=True)

<AxesSubplot:xlabel='Date'>


from sklearn.metrics import mean_squared_error

error = mean_squared_error(test['Price'], predictions)


error = np.sqrt(error)
print(error)

671.2105548504339


df=df.sort_index()

df


df=df.asfreq('d').ffill()


df.index

DatetimeIndex(['2011-12-12', '2011-12-13', '2011-12-14', '2011-12-15',
               '2011-12-16', '2011-12-17', '2011-12-18', '2011-12-19',
               '2011-12-20', '2011-12-21',
               ...
               '2022-11-22', '2022-11-23', '2022-11-24', '2022-11-25',
               '2022-11-26', '2022-11-27', '2022-11-28', '2022-11-29',
               '2022-11-30', '2022-12-01'],
              dtype='datetime64[ns]', name='Date', length=4008, freq='D')


len(df)

4008


ax = df['Price'].plot(figsize=(12,6))
ax.autoscale(axis='x',tight=True)


result = seasonal_decompose(df['Price'], model='mul')
result.plot();

df


len(df)

4008


df.index

DatetimeIndex(['2011-12-12', '2011-12-13', '2011-12-14', '2011-12-15',
               '2011-12-16', '2011-12-17', '2011-12-18', '2011-12-19',
               '2011-12-20', '2011-12-21',
               ...
               '2022-11-22', '2022-11-23', '2022-11-24', '2022-11-25',
               '2022-11-26', '2022-11-27', '2022-11-28', '2022-11-29',
               '2022-11-30', '2022-12-01'],
              dtype='datetime64[ns]', name='Date', length=4008, freq='D')


df4=df.asfreq('MS')

df4


len(df4)

132


df4['Price'].plot()

<AxesSubplot:xlabel='Date'>

df4


df4=df4.drop(columns=['year', 'day_of_month',
       'day_of_week', 'month', '6-month-SMA', '12-month-SMA', 'EWMA12',
       'TESadd12', 'TESmul12'])


result = seasonal_decompose(df4['Price'], model='mul')
result.plot();


train = df4.iloc[:125]
test = df4.iloc[125:]


stepwise_fit = auto_arima(df4['Price'], start_p=0, start_q=0,
                          max_p=2, max_q=2, m=7,
                          start_P=0, seasonal=True,
                          d=None, D=1, trace=True,
                          error_action='ignore',   # we don't want to know if an order does not work
                          suppress_warnings=True,  # we don't want convergence warnings
                          stepwise=False)           # set to stepwise

stepwise_fit.summary()

 ARIMA(0,1,0)(0,1,0)[7]             : AIC=2010.352, Time=0.05 sec
 ARIMA(0,1,0)(0,1,1)[7]             : AIC=inf, Time=0.13 sec
 ARIMA(0,1,0)(0,1,2)[7]             : AIC=inf, Time=0.24 sec
 ARIMA(0,1,0)(1,1,0)[7]             : AIC=1991.702, Time=0.17 sec
 ARIMA(0,1,0)(1,1,1)[7]             : AIC=inf, Time=0.19 sec
 ARIMA(0,1,0)(1,1,2)[7]             : AIC=inf, Time=0.83 sec
 ARIMA(0,1,0)(2,1,0)[7]             : AIC=1989.062, Time=0.14 sec
 ARIMA(0,1,0)(2,1,1)[7]             : AIC=inf, Time=0.35 sec
 ARIMA(0,1,0)(2,1,2)[7]             : AIC=inf, Time=0.49 sec
 ARIMA(0,1,1)(0,1,0)[7]             : AIC=2008.858, Time=0.05 sec
 ARIMA(0,1,1)(0,1,1)[7]             : AIC=inf, Time=0.16 sec
 ARIMA(0,1,1)(0,1,2)[7]             : AIC=inf, Time=0.35 sec
 ARIMA(0,1,1)(1,1,0)[7]             : AIC=1987.612, Time=0.15 sec
 ARIMA(0,1,1)(1,1,1)[7]             : AIC=inf, Time=0.28 sec
 ARIMA(0,1,1)(1,1,2)[7]             : AIC=inf, Time=0.81 sec
 ARIMA(0,1,1)(2,1,0)[7]             : AIC=1987.240, Time=0.20 sec
 ARIMA(0,1,1)(2,1,1)[7]             : AIC=inf, Time=0.47 sec
 ARIMA(0,1,1)(2,1,2)[7]             : AIC=inf, Time=0.58 sec
 ARIMA(0,1,2)(0,1,0)[7]             : AIC=1981.325, Time=0.14 sec
 ARIMA(0,1,2)(0,1,1)[7]             : AIC=inf, Time=0.26 sec
 ARIMA(0,1,2)(0,1,2)[7]             : AIC=inf, Time=0.79 sec
 ARIMA(0,1,2)(1,1,0)[7]             : AIC=1966.918, Time=0.15 sec
 ARIMA(0,1,2)(1,1,1)[7]             : AIC=inf, Time=0.34 sec
 ARIMA(0,1,2)(1,1,2)[7]             : AIC=inf, Time=1.07 sec
 ARIMA(0,1,2)(2,1,0)[7]             : AIC=1964.870, Time=0.32 sec
 ARIMA(0,1,2)(2,1,1)[7]             : AIC=inf, Time=0.80 sec
 ARIMA(1,1,0)(0,1,0)[7]             : AIC=2011.921, Time=0.05 sec
 ARIMA(1,1,0)(0,1,1)[7]             : AIC=inf, Time=0.22 sec
 ARIMA(1,1,0)(0,1,2)[7]             : AIC=inf, Time=0.33 sec
 ARIMA(1,1,0)(1,1,0)[7]             : AIC=1992.441, Time=0.18 sec
 ARIMA(1,1,0)(1,1,1)[7]             : AIC=inf, Time=0.24 sec
 ARIMA(1,1,0)(1,1,2)[7]             : AIC=inf, Time=0.54 sec
 ARIMA(1,1,0)(2,1,0)[7]             : AIC=1990.462, Time=0.22 sec
 ARIMA(1,1,0)(2,1,1)[7]             : AIC=inf, Time=0.46 sec
 ARIMA(1,1,0)(2,1,2)[7]             : AIC=inf, Time=0.55 sec
 ARIMA(1,1,1)(0,1,0)[7]             : AIC=inf, Time=0.09 sec
 ARIMA(1,1,1)(0,1,1)[7]             : AIC=inf, Time=0.35 sec
 ARIMA(1,1,1)(0,1,2)[7]             : AIC=inf, Time=0.67 sec
 ARIMA(1,1,1)(1,1,0)[7]             : AIC=1982.984, Time=0.29 sec
 ARIMA(1,1,1)(1,1,1)[7]             : AIC=inf, Time=0.35 sec
 ARIMA(1,1,1)(1,1,2)[7]             : AIC=inf, Time=0.97 sec
 ARIMA(1,1,1)(2,1,0)[7]             : AIC=1980.608, Time=0.76 sec
 ARIMA(1,1,1)(2,1,1)[7]             : AIC=inf, Time=0.96 sec
 ARIMA(1,1,2)(0,1,0)[7]             : AIC=1983.244, Time=0.18 sec
 ARIMA(1,1,2)(0,1,1)[7]             : AIC=inf, Time=0.52 sec
 ARIMA(1,1,2)(0,1,2)[7]             : AIC=inf, Time=0.50 sec
 ARIMA(1,1,2)(1,1,0)[7]             : AIC=1967.107, Time=0.24 sec
 ARIMA(1,1,2)(1,1,1)[7]             : AIC=inf, Time=0.74 sec
 ARIMA(1,1,2)(2,1,0)[7]             : AIC=1966.003, Time=0.48 sec
 ARIMA(2,1,0)(0,1,0)[7]             : AIC=1983.028, Time=0.03 sec
 ARIMA(2,1,0)(0,1,1)[7]             : AIC=inf, Time=0.20 sec
 ARIMA(2,1,0)(0,1,2)[7]             : AIC=inf, Time=0.36 sec
 ARIMA(2,1,0)(1,1,0)[7]             : AIC=1966.638, Time=0.14 sec
 ARIMA(2,1,0)(1,1,1)[7]             : AIC=inf, Time=0.40 sec
 ARIMA(2,1,0)(1,1,2)[7]             : AIC=inf, Time=0.84 sec
 ARIMA(2,1,0)(2,1,0)[7]             : AIC=1964.952, Time=0.21 sec
 ARIMA(2,1,0)(2,1,1)[7]             : AIC=inf, Time=0.69 sec
 ARIMA(2,1,1)(0,1,0)[7]             : AIC=1984.122, Time=0.05 sec
 ARIMA(2,1,1)(0,1,1)[7]             : AIC=inf, Time=0.52 sec
 ARIMA(2,1,1)(0,1,2)[7]             : AIC=inf, Time=0.78 sec
 ARIMA(2,1,1)(1,1,0)[7]             : AIC=1968.534, Time=0.34 sec
 ARIMA(2,1,1)(1,1,1)[7]             : AIC=inf, Time=0.61 sec
 ARIMA(2,1,1)(2,1,0)[7]             : AIC=1966.423, Time=0.40 sec
 ARIMA(2,1,2)(0,1,0)[7]             : AIC=1984.221, Time=0.11 sec
 ARIMA(2,1,2)(0,1,1)[7]             : AIC=inf, Time=0.47 sec
 ARIMA(2,1,2)(1,1,0)[7]             : AIC=1968.072, Time=0.31 sec

Best model:  ARIMA(0,1,2)(2,1,0)[7]          
Total fit time: 26.931 seconds


model = sm.tsa.statespace.SARIMAX(train['Price'],order=(0,1,2),seasonal_order=(2,1,0,7))
results = model.fit()
results.summary()


start=len(train)
end=len(train)+len(test)-1
predictions = results.predict(start=start, end=end, dynamic=False, typ='levels').rename('SARIMA Predictions')


ax = test['Price'].plot(legend=True,figsize=(12,6))
predictions.plot(legend=True)
ax.autoscale(axis='x',tight=True)


from statsmodels.tools.eval_measures import rmse

error = rmse(test['Price'], predictions)
print(f'RMSE Error: {error:11.10}')

RMSE Error:  721.883761


model = sm.tsa.statespace.SARIMAX(df4['Price'],order=(0,1,2),seasonal_order=(2,1,0,7))
results = model.fit()
fcast = results.predict(len(df4),len(df4)+7,typ='levels').rename('Forecast')


ax = df4['Price'].plot(legend=True,figsize=(12,6))
fcast.plot(legend=True)
ax.autoscale(axis='x',tight=True)

Dep. Variable:	y	No. Observations:	533
Model:	SARIMAX(5, 1, 2)	Log Likelihood	-3832.980
Date:	Sat, 05 Mar 2022	AIC	7681.960
Time:	01:08:15	BIC	7716.173
Sample:	0	HQIC	7695.350
	- 533
Covariance Type:	opg

	coef	std err	z	P>\|z\|	[0.025	0.975]
ar.L1	-0.7615	0.118	-6.450	0.000	-0.993	-0.530
ar.L2	-0.0249	0.177	-0.141	0.888	-0.372	0.322
ar.L3	-0.2767	0.112	-2.474	0.013	-0.496	-0.057
ar.L4	0.2472	0.104	2.387	0.017	0.044	0.450
ar.L5	0.4652	0.060	7.731	0.000	0.347	0.583
ma.L1	0.2908	0.128	2.270	0.023	0.040	0.542
ma.L2	-0.4657	0.141	-3.296	0.001	-0.743	-0.189
sigma2	1.053e+05	4051.333	25.980	0.000	9.73e+04	1.13e+05

Ljung-Box (L1) (Q):	0.03	Jarque-Bera (JB):	315.78
Prob(Q):	0.86	Prob(JB):	0.00
Heteroskedasticity (H):	1.13	Skew:	-0.17
Prob(H) (two-sided):	0.41	Kurtosis:	6.76

Dep. Variable:	y	No. Observations:	533
Model:	SARIMAX(2, 0, 0)x(1, 1, [1], 12)	Log Likelihood	-3896.472
Date:	Sat, 05 Mar 2022	AIC	7804.944
Time:	01:09:45	BIC	7830.478
Sample:	0	HQIC	7814.946
	- 533
Covariance Type:	opg

	coef	std err	z	P>\|z\|	[0.025	0.975]
intercept	1.3496	2.840	0.475	0.635	-4.216	6.915
ar.L1	0.7289	0.035	20.653	0.000	0.660	0.798
ar.L2	0.2268	0.035	6.496	0.000	0.158	0.295
ar.S.L12	-0.3104	0.041	-7.557	0.000	-0.391	-0.230
ma.S.L12	-0.8599	0.035	-24.544	0.000	-0.929	-0.791
sigma2	1.686e+05	7987.154	21.109	0.000	1.53e+05	1.84e+05

Data Cleaning¶

Analysis and Pre-processing¶

LSTM Modelling¶

Considering the whole dataframe for training and forecasting¶

Statistical Analysis¶

FORECASTING¶

AR(p) AutoRegressive Model¶

Fitting AR(1) Model¶

Augmented Dickey-Fuller Test¶

ARIMA¶

Ljung-Box (L1) (Q):	1.68	Jarque-Bera (JB):	44.73
Prob(Q):	0.20	Prob(JB):	0.00
Heteroskedasticity (H):	0.89	Skew:	-0.10
Prob(H) (two-sided):	0.45	Kurtosis:	4.42

Dep. Variable:	Price	No. Observations:	500
Model:	SARIMAX(5, 1, 12)	Log Likelihood	-3480.051
Date:	Sat, 05 Mar 2022	AIC	6996.102
Time:	01:09:48	BIC	7071.453
Sample:	12-18-2011	HQIC	7025.705
	- 07-11-2021
Covariance Type:	opg

	Price	Open	High	Low	Volume	year	day_of_month	day_of_week	month	6-month-SMA	12-month-SMA	EWMA12	TESadd12	TESmul12
Date
2012-01-01	5296.0	5310.0	5310.0	5293.0	3610.0	2011.0	31.0	5.0	12.0	5385.500000	5326.583333	5309.230752	5396.140112	5385.819817
2012-02-01	5325.0	5293.0	5329.0	5282.0	20450.0	2012.0	1.0	1.0	1.0	5397.166667	5310.666667	5311.636344	5486.519943	5471.741740
2012-03-01	5442.0	5332.0	5464.0	5332.0	213000.0	2012.0	1.0	1.0	1.0	5392.166667	5294.333333	5309.206588	5566.886069	5623.956505
2012-04-01	5462.0	5457.0	5498.0	5413.0	227480.0	2012.0	1.0	6.0	1.0	5371.500000	5266.416667	5285.062331	5261.384348	5293.633300
2012-05-01	5443.0	5451.0	5465.0	5402.0	203700.0	2012.0	1.0	1.0	5.0	5342.000000	5233.083333	5252.891846	5342.635430	5353.441355
2012-06-01	5345.0	5436.0	5436.0	5325.0	212280.0	2012.0	1.0	1.0	6.0	5311.500000	5200.083333	5218.326727	5346.445585	5356.327838
2012-07-01	5366.0	5358.0	5379.0	5358.0	5860.0	2012.0	1.0	6.0	7.0	5267.666667	5171.833333	5195.295223	5296.946550	5305.530232
2012-08-01	4921.0	4985.0	5025.0	4907.0	257800.0	2012.0	31.0	1.0	7.0	5011.000000	5082.416667	5075.526811	4989.423241	4993.094303
2012-09-01	5295.0	5355.0	5370.0	5275.0	210370.0	2012.0	1.0	5.0	9.0	5224.166667	5139.583333	5164.257991	5294.406043	5299.952128
2012-10-01	5318.0	5305.0	5369.0	5305.0	168370.0	2012.0	1.0	1.0	10.0	5196.500000	5116.666667	5140.486716	5234.771124	5242.802410
2012-11-01	5285.0	5316.0	5316.0	5234.0	182450.0	2012.0	1.0	1.0	11.0	5161.333333	5088.083333	5108.211574	5182.624664	5191.343465
2012-12-01	5260.0	5274.0	5308.0	5241.0	171810.0	2012.0	1.0	5.0	12.0	5124.166667	5063.666667	5076.068223	5070.934605	5079.262788
2013-01-01	5031.0	5020.0	5035.0	5020.0	21350.0	2013.0	1.0	1.0	1.0	5090.833333	5105.000000	5100.810225	5080.898990	5074.546636
2013-02-01	5049.0	5035.0	5096.0	5033.0	194400.0	2013.0	1.0	1.0	1.0	5105.666667	5113.333333	5113.502994	5111.076146	5102.110938
2013-03-01	5080.0	5055.0	5090.0	5051.0	157930.0	2013.0	1.0	1.0	1.0	5115.166667	5121.750000	5125.230811	5143.512456	5134.321939
2013-04-01	5113.0	5070.0	5122.0	5054.0	204950.0	2013.0	1.0	1.0	1.0	5123.833333	5130.166667	5133.454594	5134.756220	5130.381596
2013-05-01	5123.0	5122.0	5126.0	5116.0	4650.0	2013.0	1.0	1.0	5.0	5125.000000	5133.333333	5137.173612	5144.330051	5141.547734
2013-06-01	5273.0	5290.0	5325.0	5246.0	178890.0	2013.0	31.0	1.0	5.0	5308.333333	5424.916667	5411.151294	5249.718668	5252.099288
2013-07-01	5149.0	5120.0	5156.0	5107.0	148920.0	2013.0	1.0	1.0	7.0	5127.166667	5139.916667	5139.750632	5106.097591	5110.086894
2013-08-01	5120.0	5152.0	5169.0	5115.0	176120.0	2013.0	1.0	1.0	8.0	5119.166667	5142.416667	5138.068929	5098.266108	5100.472248
2013-09-01	5106.0	5126.0	5142.0	5092.0	178860.0	2013.0	1.0	6.0	9.0	5121.000000	5147.250000	5141.354188	5108.051899	5116.288282
2013-10-01	5132.0	5111.0	5175.0	5111.0	198270.0	2013.0	1.0	1.0	10.0	5128.333333	5154.583333	5147.782223	5111.922295	5114.424773
2013-11-01	5120.0	5125.0	5138.0	5085.0	182300.0	2013.0	1.0	1.0	11.0	5136.500000	5161.333333	5150.651718	5123.022029	5124.039174
2013-12-01	5136.0	5124.0	5149.0	5124.0	6610.0	2013.0	1.0	6.0	12.0	5141.666667	5170.333333	5156.224757	5120.543535	5126.383431
2014-01-01	6135.0	6124.0	6170.0	6123.0	8100.0	2014.0	1.0	1.0	1.0	5922.833333	5825.583333	5911.325125	5925.964866	5927.354235
2014-02-01	6016.0	6144.0	6170.0	6001.0	69780.0	2014.0	1.0	5.0	1.0	5851.166667	5795.750000	5870.656966	5849.142392	5852.259636
2014-03-01	5897.0	5994.0	5999.0	5882.0	66210.0	2014.0	1.0	5.0	1.0	5799.166667	5787.916667	5844.230960	5799.522877	5806.616818
2014-04-01	6119.0	6106.0	6139.0	6076.0	49100.0	2014.0	31.0	1.0	1.0	6043.166667	6146.083333	6106.742195	5999.439301	6004.353267
2014-05-01	6015.0	6100.0	6100.0	6004.0	56340.0	2014.0	30.0	1.0	1.0	6006.000000	6015.916667	6019.115075	5978.625381	5979.236055
2014-06-01	5846.0	5890.0	5918.0	5841.0	55510.0	2014.0	1.0	6.0	6.0	5759.000000	5797.666667	5834.636589	5783.411078	5781.887487
2014-07-01	5856.0	5857.0	5879.0	5831.0	52930.0	2014.0	1.0	1.0	7.0	5734.833333	5818.916667	5832.570514	5718.953645	5731.477058
2014-08-01	5787.0	5857.0	5874.0	5778.0	60260.0	2014.0	1.0	1.0	8.0	5729.333333	5839.750000	5828.310608	5670.929375	5679.494992
2014-09-01	5705.0	5775.0	5784.0	5700.0	54620.0	2014.0	1.0	1.0	9.0	5728.333333	5864.833333	5835.821627	5696.249748	5692.831063
2014-10-01	5704.0	5716.0	5770.0	5669.0	75850.0	2014.0	1.0	1.0	10.0	5740.333333	5900.500000	5859.607378	5689.961632	5705.786953
2014-11-01	4931.0	4992.0	5004.0	4907.0	88110.0	2014.0	31.0	1.0	10.0	4853.833333	4782.833333	4779.410548	4932.835288	4947.358153
2014-12-01	4210.0	4250.0	4349.0	4192.0	167180.0	2014.0	28.0	1.0	11.0	4188.500000	3989.416667	4017.667271	4250.710690	4250.014134
2015-01-01	3400.0	3398.0	3410.0	3383.0	14360.0	2015.0	1.0	1.0	1.0	3201.166667	3056.583333	3126.066532	3261.968237	3267.855729
2015-02-01	3391.0	3419.0	3438.0	3323.0	169070.0	2015.0	1.0	6.0	1.0	3131.666667	3021.833333	3076.260446	3110.858221	3116.919630
2015-03-01	3067.0	3061.0	3069.0	3052.0	10120.0	2015.0	28.0	5.0	1.0	3144.500000	3056.666667	3080.073738	3161.235202	3161.647389
2015-04-01	3025.0	3025.0	3055.0	2977.0	181020.0	2015.0	31.0	1.0	1.0	3156.833333	3253.833333	3243.593746	3100.629361	3111.588149
2015-05-01	3215.0	3380.0	3380.0	3190.0	186090.0	2015.0	1.0	1.0	5.0	3048.166667	2984.333333	3019.035073	3050.088696	3052.246146
2015-06-01	3069.0	3197.0	3207.0	3047.0	214950.0	2015.0	1.0	1.0	6.0	2983.333333	2962.083333	2983.405086	3030.973238	3033.139323
2015-07-01	3077.0	3053.0	3137.0	2986.0	255860.0	2015.0	1.0	1.0	7.0	2949.000000	2947.250000	2967.842375	2981.109050	2975.583553
2015-08-01	3055.0	3102.0	3119.0	3035.0	154950.0	2015.0	1.0	5.0	8.0	2926.000000	2927.250000	2947.995534	2934.396950	2935.219957
2015-09-01	2983.0	3075.0	3093.0	2945.0	157230.0	2015.0	1.0	1.0	9.0	2912.000000	2909.500000	2928.540176	2878.902237	2879.559509
2015-10-01	2979.0	3005.0	3023.0	2950.0	184180.0	2015.0	30.0	1.0	9.0	3082.666667	3078.333333	3052.000337	3037.116925	3041.912654
2015-11-01	3068.0	3013.0	3076.0	2983.0	182300.0	2015.0	30.0	1.0	10.0	3049.500000	2937.916667	2965.901426	3085.241354	3082.883219
2015-12-01	2890.0	2971.0	2973.0	2864.0	140490.0	2015.0	1.0	1.0	12.0	2912.000000	2891.916667	2918.638390	2856.911919	2858.649951
2016-01-01	2480.0	2475.0	2497.0	2465.0	24880.0	2016.0	1.0	1.0	1.0	2356.833333	2198.500000	2264.860599	2404.587246	2401.798111
2016-02-01	2286.0	2299.0	2345.0	2231.0	281320.0	2016.0	29.0	1.0	1.0	2169.333333	2065.750000	2130.753797	2091.490319	2105.337708
2016-03-01	2321.0	2298.0	2332.0	2230.0	234090.0	2016.0	29.0	1.0	1.0	2382.333333	2451.666667	2438.840929	2335.812520	2339.540600
2016-04-01	2465.0	2494.0	2566.0	2433.0	290300.0	2016.0	1.0	1.0	1.0	2291.666667	2154.333333	2225.744344	2328.654768	2328.498812
2016-05-01	2407.0	2467.0	2476.0	2397.0	212230.0	2016.0	1.0	6.0	5.0	2219.166667	2108.833333	2182.243315	2235.394491	2238.975244
2016-06-01	2291.0	2419.0	2422.0	2267.0	268230.0	2016.0	1.0	1.0	6.0	2159.833333	2079.500000	2141.378464	2197.166457	2197.259274
2016-07-01	2254.0	2275.0	2291.0	2156.0	350680.0	2016.0	1.0	1.0	7.0	2130.166667	2068.416667	2114.174548	2132.524633	2137.213813
2016-08-01	2244.0	2262.0	2285.0	2196.0	260260.0	2016.0	1.0	1.0	8.0	2087.166667	2055.583333	2088.751739	2035.977012	2044.969573
2016-09-01	3003.0	3129.0	3129.0	2996.0	201120.0	2016.0	31.0	1.0	8.0	2975.333333	3008.583333	3003.322380	2923.189755	2927.772685
2016-10-01	3212.0	3190.0	3223.0	3146.0	167460.0	2016.0	30.0	1.0	9.0	3289.166667	3326.333333	3302.414867	3265.341163	3262.744587
2016-11-01	2089.0	2215.0	2226.0	2047.0	260399.0	2016.0	1.0	1.0	11.0	2040.166667	2052.083333	2060.524782	2025.437845	2029.925429
2016-12-01	2030.0	2077.0	2161.0	2023.0	326490.0	2016.0	1.0	1.0	12.0	2017.000000	2068.583333	2055.347469	2016.573955	2029.193217
2017-01-01	3650.0	3674.0	3681.0	3638.0	56910.0	2016.0	30.0	1.0	12.0	3644.000000	3609.833333	3618.498902	3658.496272	3662.971720
2017-02-01	3685.0	3666.0	3698.0	3663.0	11770.0	2017.0	1.0	1.0	1.0	3631.333333	3605.250000	3612.771429	3617.337344	3623.958168
2017-03-01	3590.0	3685.0	3780.0	3552.0	144490.0	2017.0	1.0	1.0	1.0	3602.666667	3589.833333	3599.638962	3646.998182	3655.578386
2017-04-01	3621.0	3599.0	3628.0	3557.0	113750.0	2017.0	1.0	5.0	1.0	3602.500000	3581.666667	3601.391500	3640.433334	3653.902108
2017-05-01	3636.0	3616.0	3672.0	3584.0	129669.0	2017.0	1.0	1.0	5.0	3601.166667	3583.083333	3597.826319	3626.344016	3614.280279
2017-06-01	3682.0	3653.0	3700.0	3635.0	123120.0	2017.0	1.0	1.0	6.0	3592.833333	3581.416667	3590.885649	3576.893408	3576.773055
2017-07-01	2968.0	2924.0	2972.0	2924.0	109150.0	2017.0	30.0	1.0	6.0	2971.166667	2957.166667	2981.338187	3014.202849	3015.515597
2017-08-01	3183.0	3200.0	3214.0	3165.0	127710.0	2017.0	31.0	1.0	7.0	3150.166667	3127.500000	3131.636133	3138.860709	3137.489172
2017-09-01	3574.0	3665.0	3674.0	3564.0	110750.0	2017.0	1.0	1.0	9.0	3575.666667	3578.250000	3574.319404	3555.993086	3552.123006
2017-10-01	3513.0	3560.0	3575.0	3500.0	127340.0	2017.0	1.0	6.0	10.0	3579.166667	3582.833333	3574.377477	3591.319297	3590.492531
2017-11-01	3589.0	3500.0	3597.0	3478.0	162270.0	2017.0	1.0	1.0	11.0	3577.000000	3590.750000	3585.537019	3599.806776	3601.309517
2017-12-01	3613.0	3565.0	3644.0	3550.0	123010.0	2017.0	1.0	1.0	12.0	3560.833333	3590.083333	3584.907386	3589.531387	3583.281357
2018-01-01	3829.0	3858.0	3858.0	3782.0	15270.0	2018.0	1.0	1.0	1.0	3878.333333	3973.000000	3942.630264	3854.599161	3833.405165
2018-02-01	3824.0	3866.0	3866.0	3817.0	100300.0	2018.0	1.0	1.0	1.0	3907.333333	3994.333333	3963.290312	3919.394969	3920.946676
2018-03-01	3903.0	3834.0	3909.0	3827.0	114980.0	2018.0	1.0	1.0	1.0	3942.666667	4016.333333	3988.615823	3910.665099	3905.065400
2018-04-01	3921.0	3910.0	3950.0	3903.0	110540.0	2018.0	1.0	6.0	1.0	3975.500000	4027.500000	4004.182336	3908.894635	3907.424610
2018-05-01	3887.0	3922.0	3929.0	3866.0	102580.0	2018.0	1.0	1.0	5.0	3999.500000	4037.833333	4019.306397	3963.642509	3967.807389
2018-06-01	4517.0	4609.0	4613.0	4500.0	131570.0	2018.0	31.0	1.0	5.0	4412.166667	4443.833333	4469.386356	4402.707512	4419.303926
2018-07-01	5086.0	5045.0	5105.0	5010.0	102690.0	2018.0	29.0	1.0	6.0	5085.833333	4986.750000	5001.219850	5094.676693	5087.087590
2018-08-01	3906.0	3900.0	3933.0	3892.0	93950.0	2018.0	1.0	1.0	8.0	4037.666667	4056.416667	4043.362106	4048.607706	4032.607360
2018-09-01	4003.0	3927.0	4010.0	3927.0	122910.0	2018.0	1.0	5.0	9.0	4067.666667	4075.583333	4068.337034	4059.827225	4047.450086
2018-10-01	4036.0	4016.0	4059.0	4016.0	114860.0	2018.0	1.0	1.0	10.0	4081.333333	4091.166667	4080.216495	4062.517285	4062.621396
2018-11-01	4100.0	4040.0	4123.0	4040.0	123580.0	2018.0	1.0	1.0	11.0	4090.000000	4102.916667	4088.255857	4064.007356	4066.888680
2018-12-01	4065.0	4083.0	4083.0	4007.0	116560.0	2018.0	1.0	5.0	12.0	4079.500000	4103.416667	4086.120559	4091.670684	4099.999929
2019-01-01	3177.0	3208.0	3212.0	3152.0	21470.0	2019.0	1.0	1.0	1.0	3342.333333	3504.500000	3462.691468	3317.656141	3336.820510
2019-02-01	3328.0	3168.0	3360.0	3114.0	284910.0	2019.0	1.0	1.0	1.0	3427.166667	3547.083333	3514.635371	3324.389723	3319.176737
2019-03-01	3285.0	3277.0	3340.0	3202.0	262190.0	2019.0	1.0	1.0	1.0	3485.500000	3587.833333	3548.569074	3403.400891	3389.626834
2019-04-01	3348.0	3314.0	3439.0	3304.0	280100.0	2019.0	1.0	1.0	1.0	3543.333333	3637.083333	3596.490724	3478.335555	3477.091943
2019-05-01	4467.0	4420.0	4519.0	4420.0	216060.0	2019.0	30.0	1.0	1.0	4347.166667	4341.666667	4334.897200	4355.224073	4350.851484
2019-06-01	3775.0	3973.0	3973.0	3758.0	297190.0	2019.0	31.0	1.0	5.0	3686.000000	3679.083333	3726.324722	3688.232783	3677.746451
2019-07-01	3442.0	3381.0	3481.0	3374.0	278240.0	2019.0	1.0	1.0	7.0	3590.000000	3670.500000	3641.670856	3543.569241	3545.787285
2019-08-01	3474.0	3422.0	3513.0	3401.0	256440.0	2019.0	1.0	1.0	8.0	3631.333333	3695.416667	3677.974648	3657.550415	3665.828259
2019-09-01	3686.0	3525.0	3705.0	3525.0	275220.0	2019.0	1.0	6.0	9.0	3666.666667	3721.833333	3715.060948	3643.925485	3657.034471
2019-10-01	3678.0	3655.0	3719.0	3623.0	223140.0	2019.0	1.0	1.0	10.0	3667.000000	3732.333333	3720.344756	3638.015147	3701.817180
2019-11-01	3632.0	3693.0	3764.0	3611.0	233400.0	2019.0	1.0	1.0	11.0	3690.166667	3732.666667	3728.043803	3643.352437	3609.976614
2019-12-01	3980.0	4173.0	4180.0	3958.0	335810.0	2019.0	29.0	1.0	11.0	4096.333333	4153.250000	4138.866979	4088.901384	4238.071681
2020-01-01	4380.0	4374.0	4389.0	4366.0	21020.0	2020.0	1.0	1.0	1.0	4419.000000	4290.666667	4297.681996	4467.094482	4495.838580
2020-02-01	4343.0	4376.0	4388.0	4332.0	329720.0	2020.0	1.0	5.0	1.0	4395.166667	4271.166667	4282.715086	4526.141342	4560.022996
2020-03-01	4499.0	4360.0	4603.0	4360.0	514490.0	2020.0	1.0	6.0	1.0	4371.666667	4257.750000	4271.754192	4529.682937	4719.792740
2020-04-01	1680.0	1654.0	1694.0	1638.0	166990.0	2020.0	31.0	1.0	1.0	1897.833333	1584.833333	1679.855527	1792.364029	1829.607228
2020-05-01	1315.0	1230.0	1423.0	1230.0	197650.0	2020.0	30.0	1.0	1.0	1648.666667	1811.083333	1805.072595	1566.019280	1577.976517
2020-06-01	4538.0	4525.0	4670.0	4518.0	413100.0	2020.0	1.0	1.0	6.0	4310.500000	4231.666667	4230.436773	4377.289199	4344.720301
2020-07-01	4494.0	4511.0	4538.0	4466.0	344580.0	2020.0	1.0	1.0	7.0	4243.833333	4190.833333	4174.516186	4297.073176	4344.911874
2020-08-01	4260.0	4519.0	4590.0	4243.0	612610.0	2020.0	1.0	5.0	8.0	4178.166667	4143.916667	4116.428220	4260.541712	4276.016679
2020-09-01	4237.0	4250.0	4302.0	4178.0	437290.0	2020.0	1.0	1.0	9.0	4162.333333	4111.666667	4090.324260	4218.411029	4242.525829
2020-10-01	4202.0	4240.0	4247.0	4172.0	355280.0	2020.0	1.0	1.0	10.0	4147.166667	4073.833333	4063.655943	4221.587881	4292.215377
2020-11-01	2642.0	2691.0	2729.0	2630.0	115420.0	2020.0	30.0	1.0	10.0	2787.833333	2920.583333	2894.069373	2784.911299	2778.465973
2020-12-01	3326.0	3331.0	3398.0	3310.0	50430.0	2020.0	30.0	1.0	11.0	3365.000000	3398.250000	3398.712040	3318.663857	3323.107599
2021-01-01	3527.0	3533.0	3559.0	3511.0	1400.0	2021.0	1.0	1.0	1.0	3657.666667	3757.250000	3724.882343	3549.245050	3555.112295
2021-02-01	3820.0	3828.0	3888.0	3801.0	91030.0	2021.0	29.0	1.0	1.0	4008.500000	4146.583333	4111.786418	3967.915520	4001.678431
2021-03-01	4604.0	4636.0	4674.0	4586.0	101360.0	2021.0	26.0	1.0	1.0	4599.833333	4669.250000	4601.976231	4508.770363	4507.158762
2021-04-01	3494.0	3583.0	3643.0	3457.0	60390.0	2021.0	1.0	1.0	1.0	3711.000000	3786.000000	3760.860951	3665.547060	3667.370359
2021-05-01	3664.0	3504.0	3675.0	3466.0	50360.0	2021.0	1.0	5.0	5.0	3776.333333	3820.666667	3809.381124	3742.485274	3748.908719
2021-06-01	3721.0	3673.0	3727.0	3626.0	37300.0	2021.0	1.0	1.0	6.0	3810.833333	3839.833333	3835.814056	3781.184903	3779.083840
2021-07-01	3738.0	3733.0	3755.0	3706.0	25930.0	2021.0	1.0	1.0	7.0	3840.500000	3849.333333	3856.689338	3836.683942	3831.326288
2021-08-01	3802.0	3749.0	3808.0	3738.0	22400.0	2021.0	1.0	6.0	8.0	3855.000000	3857.750000	3878.269218	3833.209364	3835.484395
2021-09-01	5026.0	5067.0	5077.0	4983.0	49510.0	2021.0	31.0	1.0	8.0	5044.000000	5098.000000	5117.566326	5037.179970	5054.625276
2021-10-01	5571.0	5553.0	5648.0	5432.0	102540.0	2021.0	30.0	1.0	9.0	5763.833333	5921.166667	5873.562709	5718.555592	5708.063326
2021-11-01	3847.0	3810.0	3856.0	3791.0	23490.0	2021.0	1.0	1.0	11.0	3856.833333	3865.333333	3892.136349	3876.118742	3873.018191
2021-12-01	3886.0	3839.0	3903.0	3832.0	23320.0	2021.0	1.0	1.0	12.0	3861.000000	3863.666667	3900.342958	3853.254353	3886.659903
2022-01-01	5625.0	5706.0	5725.0	5603.0	57490.0	2021.0	31.0	1.0	12.0	5772.666667	5925.666667	5911.500287	5696.002002	5699.057019
2022-02-01	6561.0	6591.0	6607.0	6453.0	40990.0	2022.0	31.0	1.0	1.0	6677.166667	6762.833333	6716.636172	6620.669363	6669.785132
2022-03-01	5677.0	5638.0	5695.0	5544.0	70090.0	2022.0	1.0	1.0	1.0	5801.000000	5984.583333	5963.668504	5775.812038	5882.364634
2022-04-01	5761.0	5685.0	5788.0	5650.0	62100.0	2022.0	1.0	1.0	1.0	5855.500000	6051.333333	6015.881431	5838.634502	5861.602332
2022-05-01	5828.0	5730.0	5844.0	5695.0	64170.0	2022.0	1.0	6.0	5.0	5914.166667	6104.333333	6062.319560	5801.759709	5791.258625
2022-06-01	5899.0	5800.0	5975.0	5709.0	84090.0	2022.0	1.0	1.0	6.0	5956.333333	6145.250000	6105.027512	5798.462529	5825.400945
2022-07-01	5846.0	5955.0	5978.0	5836.0	64980.0	2022.0	1.0	1.0	7.0	6009.500000	6173.666667	6142.595589	5864.679430	5868.697609
2022-08-01	6800.0	6862.0	6901.0	6779.0	50800.0	2022.0	1.0	5.0	7.0	6833.333333	6867.333333	6842.024561	6722.956989	6859.083544
2022-09-01	6700.0	6809.0	6837.0	6616.0	76980.0	2022.0	1.0	1.0	8.0	6848.500000	6873.916667	6850.480991	6782.637509	6816.956900
2022-10-01	5795.0	5853.0	5890.0	5775.0	74340.0	2022.0	1.0	5.0	10.0	6078.666667	6218.000000	6196.706801	6038.449341	6039.483947
2022-11-01	6004.0	5834.0	6021.0	5812.0	81850.0	2022.0	1.0	1.0	11.0	6168.166667	6281.333333	6270.040291	6083.566134	6076.891243
2022-12-01	6113.0	6003.0	6125.0	5989.0	59690.0	2022.0	1.0	1.0	12.0	6247.166667	6326.250000	6318.643014	6170.842926	6211.022368

Ljung-Box (L1) (Q):	0.13	Jarque-Bera (JB):	101.96
Prob(Q):	0.71	Prob(JB):	0.00
Heteroskedasticity (H):	4.16	Skew:	-0.33
Prob(H) (two-sided):	0.00	Kurtosis:	7.39

Ljung-Box (L1) (Q):	0.19	Jarque-Bera (JB):	129.04
Prob(Q):	0.66	Prob(JB):	0.00
Heteroskedasticity (H):	3.92	Skew:	-0.50
Prob(H) (two-sided):	0.00	Kurtosis:	8.05

	Date	Price	Open	High	Low	Volume	Chg%
0	Feb 25, 2022	6848	7210	7220	6777	136.10K	-5.87%
1	Feb 24, 2022	7275	6940	7617	6940	148.58K	5.76%
2	Feb 23, 2022	6879	6900	7014	6774	67.95K	-0.55%
3	Feb 22, 2022	6917	6765	7125	6649	80.37K	0.71%
4	Feb 21, 2022	6868	6739	6918	6670	53.96K	0.35%
5	Feb 18, 2022	6844	6824	6938	6669	8.80K	0.04%
6	Feb 17, 2022	6841	6885	7012	6814	23.81K	-2.92%
7	Feb 16, 2022	7047	6907	7132	6900	28.73K	2.26%
8	Feb 15, 2022	6891	7153	7190	6824	55.62K	-3.05%
9	Feb 14, 2022	7108	6949	7157	6949	56.82K	2.75%
10	Feb 11, 2022	6918	6765	6935	6720	54.85K	1.75%
11	Feb 10, 2022	6799	6699	6882	6691	75.14K	1.86%
12	Feb 09, 2022	6675	6692	6777	6618	67.23K	-0.37%
13	Feb 08, 2022	6700	6809	6837	6616	76.98K	-1.47%
14	Feb 07, 2022	6800	6862	6901	6779	50.80K	-1.66%
15	Feb 04, 2022	6915	6714	6958	6714	59.51K	4.13%
16	Feb 03, 2022	6641	6577	6684	6501	51.96K	0.97%
17	Feb 02, 2022	6577	6600	6706	6524	65.95K	0.12%
18	Feb 01, 2022	6569	6575	6650	6478	55.62K	0.12%
19	Jan 31, 2022	6561	6591	6607	6453	40.99K	0.28%
20	Jan 28, 2022	6543	6545	6667	6495	58.68K	-0.18%
21	Jan 27, 2022	6555	6427	6660	6427	57.48K	2.78%
22	Jan 25, 2022	6378	6250	6388	6218	58.94K	2.21%
23	Jan 24, 2022	6240	6349	6415	6136	66.68K	-1.25%
24	Jan 21, 2022	6319	6363	6368	6200	64.43K	-1.22%
25	Jan 20, 2022	6397	6370	6480	6340	45.56K	-1.25%
26	Jan 19, 2022	6478	6452	6556	6396	5.47K	2.31%
27	Jan 18, 2022	6332	6298	6385	6298	13.68K	1.13%
28	Jan 17, 2022	6261	6233	6285	6203	17.44K	0.69%
29	Jan 14, 2022	6218	6060	6237	6046	43.10K	2.25%
30	Jan 13, 2022	6081	6087	6122	6053	34.06K	-0.52%
31	Jan 12, 2022	6113	6003	6125	5989	59.69K	1.82%
32	Jan 11, 2022	6004	5834	6021	5812	81.85K	3.61%
33	Jan 10, 2022	5795	5853	5890	5775	74.34K	-0.87%
34	Jan 07, 2022	5846	5955	5978	5836	64.98K	-0.90%
35	Jan 06, 2022	5899	5800	5975	5709	84.09K	1.22%
36	Jan 05, 2022	5828	5730	5844	5695	64.17K	1.16%
37	Jan 04, 2022	5761	5685	5788	5650	62.10K	1.48%
38	Jan 03, 2022	5677	5638	5695	5544	70.09K	0.92%
39	Dec 31, 2021	5625	5706	5725	5603	57.49K	-1.92%

	Price	Open	High	Low	Volume	Chg%
Date
2022-02-25	6848	7210	7220	6777	136.10K	-5.87%
2022-02-24	7275	6940	7617	6940	148.58K	5.76%
2022-02-23	6879	6900	7014	6774	67.95K	-0.55%
2022-02-22	6917	6765	7125	6649	80.37K	0.71%
2022-02-21	6868	6739	6918	6670	53.96K	0.35%
2022-02-18	6844	6824	6938	6669	8.80K	0.04%
2022-02-17	6841	6885	7012	6814	23.81K	-2.92%
2022-02-16	7047	6907	7132	6900	28.73K	2.26%
2022-02-15	6891	7153	7190	6824	55.62K	-3.05%
2022-02-14	7108	6949	7157	6949	56.82K	2.75%
2022-11-02	6918	6765	6935	6720	54.85K	1.75%
2022-10-02	6799	6699	6882	6691	75.14K	1.86%
2022-09-02	6675	6692	6777	6618	67.23K	-0.37%
2022-08-02	6700	6809	6837	6616	76.98K	-1.47%
2022-07-02	6800	6862	6901	6779	50.80K	-1.66%
2022-04-02	6915	6714	6958	6714	59.51K	4.13%
2022-03-02	6641	6577	6684	6501	51.96K	0.97%
2022-02-02	6577	6600	6706	6524	65.95K	0.12%
2022-01-02	6569	6575	6650	6478	55.62K	0.12%
2022-01-31	6561	6591	6607	6453	40.99K	0.28%
2022-01-28	6543	6545	6667	6495	58.68K	-0.18%
2022-01-27	6555	6427	6660	6427	57.48K	2.78%
2022-01-25	6378	6250	6388	6218	58.94K	2.21%
2022-01-24	6240	6349	6415	6136	66.68K	-1.25%
2022-01-21	6319	6363	6368	6200	64.43K	-1.22%
2022-01-20	6397	6370	6480	6340	45.56K	-1.25%
2022-01-19	6478	6452	6556	6396	5.47K	2.31%
2022-01-18	6332	6298	6385	6298	13.68K	1.13%
2022-01-17	6261	6233	6285	6203	17.44K	0.69%
2022-01-14	6218	6060	6237	6046	43.10K	2.25%
2022-01-13	6081	6087	6122	6053	34.06K	-0.52%
2022-12-01	6113	6003	6125	5989	59.69K	1.82%
2022-11-01	6004	5834	6021	5812	81.85K	3.61%
2022-10-01	5795	5853	5890	5775	74.34K	-0.87%
2022-07-01	5846	5955	5978	5836	64.98K	-0.90%
2022-06-01	5899	5800	5975	5709	84.09K	1.22%
2022-05-01	5828	5730	5844	5695	64.17K	1.16%
2022-04-01	5761	5685	5788	5650	62.10K	1.48%
2022-03-01	5677	5638	5695	5544	70.09K	0.92%

	Price	Open	High	Low	Volume	Chg%
Date
2022-02-25	6848	7210	7220	6777	136.10K	-5.87%
2022-02-24	7275	6940	7617	6940	148.58K	5.76%
2022-02-23	6879	6900	7014	6774	67.95K	-0.55%
2022-02-22	6917	6765	7125	6649	80.37K	0.71%
2022-02-21	6868	6739	6918	6670	53.96K	0.35%
2022-02-18	6844	6824	6938	6669	8.80K	0.04%
2022-02-17	6841	6885	7012	6814	23.81K	-2.92%
2022-02-16	7047	6907	7132	6900	28.73K	2.26%
2022-02-15	6891	7153	7190	6824	55.62K	-3.05%
2022-02-14	7108	6949	7157	6949	56.82K	2.75%
2022-11-02	6918	6765	6935	6720	54.85K	1.75%
2022-10-02	6799	6699	6882	6691	75.14K	1.86%
2022-09-02	6675	6692	6777	6618	67.23K	-0.37%
2022-08-02	6700	6809	6837	6616	76.98K	-1.47%
2022-07-02	6800	6862	6901	6779	50.80K	-1.66%
2022-04-02	6915	6714	6958	6714	59.51K	4.13%
2022-03-02	6641	6577	6684	6501	51.96K	0.97%
2022-02-02	6577	6600	6706	6524	65.95K	0.12%
2022-01-02	6569	6575	6650	6478	55.62K	0.12%
2022-01-31	6561	6591	6607	6453	40.99K	0.28%
2022-01-28	6543	6545	6667	6495	58.68K	-0.18%
2022-01-27	6555	6427	6660	6427	57.48K	2.78%
2022-01-25	6378	6250	6388	6218	58.94K	2.21%
2022-01-24	6240	6349	6415	6136	66.68K	-1.25%
2022-01-21	6319	6363	6368	6200	64.43K	-1.22%
2022-01-20	6397	6370	6480	6340	45.56K	-1.25%
2022-01-19	6478	6452	6556	6396	5.47K	2.31%
2022-01-18	6332	6298	6385	6298	13.68K	1.13%
2022-01-17	6261	6233	6285	6203	17.44K	0.69%
2022-01-14	6218	6060	6237	6046	43.10K	2.25%
2022-01-13	6081	6087	6122	6053	34.06K	-0.52%
2022-12-01	6113	6003	6125	5989	59.69K	1.82%
2022-11-01	6004	5834	6021	5812	81.85K	3.61%
2022-10-01	5795	5853	5890	5775	74.34K	-0.87%
2022-07-01	5846	5955	5978	5836	64.98K	-0.90%
2022-06-01	5899	5800	5975	5709	84.09K	1.22%
2022-05-01	5828	5730	5844	5695	64.17K	1.16%
2022-04-01	5761	5685	5788	5650	62.10K	1.48%
2022-03-01	5677	5638	5695	5544	70.09K	0.92%

	Price	Open	High	Low	Volume
Date
2022-02-25	6848	7210	7220	6777	136100
2022-02-24	7275	6940	7617	6940	148580
2022-02-23	6879	6900	7014	6774	67950
2022-02-22	6917	6765	7125	6649	80370
2022-02-21	6868	6739	6918	6670	53960
2022-02-18	6844	6824	6938	6669	8800
2022-02-17	6841	6885	7012	6814	23810
2022-02-16	7047	6907	7132	6900	28730
2022-02-15	6891	7153	7190	6824	55620
2022-02-14	7108	6949	7157	6949	56820
2022-11-02	6918	6765	6935	6720	54850
2022-10-02	6799	6699	6882	6691	75140
2022-09-02	6675	6692	6777	6618	67230
2022-08-02	6700	6809	6837	6616	76980
2022-07-02	6800	6862	6901	6779	50800
2022-04-02	6915	6714	6958	6714	59510
2022-03-02	6641	6577	6684	6501	51960
2022-02-02	6577	6600	6706	6524	65950
2022-01-02	6569	6575	6650	6478	55620
2022-01-31	6561	6591	6607	6453	40990
2022-01-28	6543	6545	6667	6495	58680
2022-01-27	6555	6427	6660	6427	57480
2022-01-25	6378	6250	6388	6218	58940
2022-01-24	6240	6349	6415	6136	66680
2022-01-21	6319	6363	6368	6200	64430
2022-01-20	6397	6370	6480	6340	45560
2022-01-19	6478	6452	6556	6396	5470
2022-01-18	6332	6298	6385	6298	13680
2022-01-17	6261	6233	6285	6203	17440
2022-01-14	6218	6060	6237	6046	43100
2022-01-13	6081	6087	6122	6053	34060
2022-12-01	6113	6003	6125	5989	59690
2022-11-01	6004	5834	6021	5812	81850
2022-10-01	5795	5853	5890	5775	74340
2022-07-01	5846	5955	5978	5836	64980
2022-06-01	5899	5800	5975	5709	84090
2022-05-01	5828	5730	5844	5695	64170
2022-04-01	5761	5685	5788	5650	62100
2022-03-01	5677	5638	5695	5544	70090